INDEX

Explanations

negative contractions and affirmative statements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

earch

-0.17

/*č↵

-0.16

.scalablytyped

-0.16

 BITS

-0.15

iley

-0.14

ernel

-0.14

oyal

-0.14

ÐĲÑĢÑħÑĸÐ²

-0.14

ãĥ³ãĥĨãĤ£

-0.14

illez

-0.14

POSITIVE LOGITS

 moon

0.15

ups

0.14

udas

0.14

det

0.14

XL

0.14

bet

0.13

apus

0.13

åĳ½

0.13

 stead

0.13

Activations Density 0.001%

negative contractions and affirmative statements

No Comments

No Known Activations